{"id":"W4408593358","doi":"10.1101/2025.03.13.643153","title":"Using semantic search to find publicly available gene-expression datasets","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; Expression (computer science); Computational biology; Biology; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.006259258,0.001614276,0.001264396,0.01619274,0.00122589,0.001873407,0.001617718,0.001628697,0.003269051],"category_scores_gemma":[0.02683171,0.0004237912,0.002592282,0.01284488,0.0008384394,0.006365268,0.00316879,0.001186767,0.001418786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001777899,"about_ca_system_score_gemma":0.00315759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005298687,"about_ca_topic_score_gemma":0.01475952,"domain_scores_codex":[0.9953834,0.001961478,0.0006627606,0.0009724806,0.0008219489,0.0001978999],"domain_scores_gemma":[0.9883709,0.008164312,0.0007738285,0.001500129,0.0009623033,0.0002286187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002422945,0.00205429,0.06592678,0.009561636,0.00224567,0.002311676,0.003564268,0.0825443,0.02694357,0.08754615,0.1051889,0.6096898],"study_design_scores_gemma":[0.0005826235,0.0008595849,0.01958259,0.0008626761,0.0009820692,0.001218513,0.005027115,0.625156,0.01983421,0.1994429,0.1261616,0.0002898918],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3239344,0.009204728,0.4716382,0.007426901,0.0005514337,0.001395151,0.1334447,0.03337531,0.01902913],"genre_scores_gemma":[0.4047076,0.001783976,0.4256521,0.001123026,0.0001277527,0.0009109298,0.163872,0.0006700329,0.001152682],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9983823,"threshold_uncertainty_score":0.03310251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03698783048375662,"score_gpt":0.2840643064826048,"score_spread":0.2470764759988482,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}